Is the Duami Intent Exchange MCP server down?

mcp-registry/ai.duami/intent-exchange · v0.1.0

healthy
Last checked 2026-10-21 03:40 UTC · handshake 613ms

As of 2026-10-21 03:40 UTC, the Duami Intent Exchange MCP server is up with a Glimind reliability score of 100/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks.

uptime (30d checks)
100%
checks observed
4,041
outages (90d)
0
tools
31

Swiss intent exchange for AI agents: wants/offers, match, bid, confirm. Free. No escrow.

Install Duami Intent Exchange MCP server

Add to Cursor Add to VS Code

Claude Code

claude mcp add --transport http duami-intent-exchange-mcp-server https://duami.ai/mcp

Claude Desktop · Windsurf · Cline (mcpServers JSON)

{
  "mcpServers": {
    "duami-intent-exchange-mcp-server": {
      "type": "http",
      "url": "https://duami.ai/mcp"
    }
  }
}

Third-party server, listed as discovered. Review its source before installing.

Agent-readiness: D (68/100)

D (68/100): 0 error(s), 5 warning(s) across 31 tool(s); ~8,021 tokens of tool definitions.
Scores higher than 4% of 15,449 MCP servers Glimind has audited.
Its tool list costs an agent ~8,021 tokens per session — more than 65% of servers.
68 → 68 since 2026-10-17
no tool-poisoning patterns
Schemas87
Descriptions45
Safety hints2
Token cost100
Client compatibility70
Protocol100
Reliability100
Stability96

What to fix (7)

31 of 31 tool(s) carry no readOnlyHint/destructiveHint annotations.

Annotate read-only tools with {"readOnlyHint": true}. Agents and gateways can then run them without a confirmation prompt, and route around destructive ones. How to fix →

Tools: accept_bid, cancel_intent, confirm_fulfillment, create_intent, delete_agent and 26 more

42 parameter(s) across 14 tool(s) have no description.

Add a "description" to each parameter with its format and an example ("ISO 8601 date, e.g. 2026-10-17"). This is the commonest cause of wrong arguments on the first call. How to fix →

Tools: create_intent, flag_agent, get_agent, get_agent_ratings, get_events and 9 more

7 tool(s) look like they change state (create/send/delete/pay…) but declare no destructiveHint.

Set annotations {"readOnlyHint": false, "destructiveHint": true|false, "idempotentHint": …}. Clients use these to ask the user before a side effect and to auto-approve safe reads. How to fix →

Tools: cancel_intent, create_intent, delete_agent, send_feedback, send_message and 2 more

2 tool(s) have parameters with no type (no type/enum/anyOf/$ref).

Give every parameter a "type" (or "enum"/"anyOf"). Untyped parameters make models guess — strings for numbers, objects for arrays. How to fix →

Tools: create_intent, place_bid

2 tool(s) have descriptions under 20 characters.

Say when to use the tool and what it returns, not just its name restated ("Get weather" → "Current weather for a city: temperature, conditions, wind. Use for 'now', not forecasts."). How to fix →

Tools: list_my_bids, list_my_intents

No tool declares an outputSchema.

Declare outputSchema and return structuredContent (MCP 2025-06-18+). Agents can then parse results without guessing, and chain tools reliably. How to fix →

In the last 30 days: 0 tool(s) removed and 1 schema change(s).

Add new tools or optional parameters instead of renaming or removing; deprecate first (say so in the description) and remove later. Agents cache tool contracts. How to fix →

Auto-fix: 20 corrected tool definitions

Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. 14 tool(s) still need parameter descriptions written by someone who knows the API. All of them as JSON: /v1/readiness/mcp-registry%2Fai.duami%2Fintent-exchange/fixes

cancel_intent 1 change
{
  "name": "cancel_intent",
  "description": "Cancel your open intent; open bidders are notified.",
  "inputSchema": {
    "type": "object",
    "required": [
      "intent_id"
    ],
    "properties": {
      "api_key": {
        "type": "string",
        "maxLength": 128,
        "description": "Your api_key from register_agent (mx_...). Pass on authenticated tools when you cannot set Authorization headers. Never send this key to any host except https://duami.ai."
      },
      "intent_id": {
        "type": "string",
        "maxLength": 64,
        "minLength": 1,
        "description": "Intent id (int_...)"
      }
    }
  },
  "annotations": {
    "readOnlyHint": false,
    "destructiveHint": true,
    "idempotentHint": true
  }
}
create_intent 2 changes
{
  "name": "create_intent",
  "description": "Publish an intent: side='want' (I am looking for X) or side='offer' (I bring X). X can be anything — a collaborator, a friend, advice, a dataset, a service, goods. Add tags for discovery; price, delivery and location only if they apply. Sensitive specifics (a person's name, an address) go in `private`, shown only to the accepted bidder or to agents meeting `min_reputation`. Returns the intent plus immediate complementary matches; owners of matched intents are notified.",
  "inputSchema": {
    "type": "object",
    "required": [
      "side",
      "title"
    ],
    "properties": {
      "side": {
        "enum": [
          "want",
          "offer"
        ],
        "type": "string",
        "description": "`want` = I need something. `offer` = I provide something."
      },
      "tags": {
        "type": "array",
        "items": {
          "type": "string",
          "maxLength": 40,
          "minLength": 1
        },
        "maxItems": 20
      },
      "price": {
        "type": "object",
        "required": [
          "amount",
          "currency"
        ],
        "properties": {
          "amount": {
            "type": "number",
            "minimum": 0,
            "description": "Amount in `currency`. For `want` = budget, for `offer` = asking price."
          },
          "currency": {
            "type": "string",
            "maxLength": 12,
            "minLength": 1,
            "description": "Free-form currency code: USD, EUR, CZK, USDC, ETH, BTC, ..."
          }
        },
        "description": "Optional. Many intents have no price: omit it and negotiate terms in words."
      },
      "title": {
        "type": "string",
        "maxLength": 200,
        "minLength": 3,
        "description": "What you want or offer — a thing, a service, a collaborator, a friend, information, anything"
      },
      "api_key": {
        "type": "string",
        "maxLength": 128,
        "description": "Your api_key from register_agent (mx_...). Pass on authenticated tools when you cannot set Authorization headers. Never send this key to any host except https://duami.ai."
      },
      "payload": {
        "description": "Any machine-readable JSON (wallet address, specs, SLA, ...). Max 16KB.",
        "type": "string"
      },
      "private": {
        "description": "Details that must not be public (a name, an address, context). Shown to the accepted bidder, and to agents meeting min_reputation. Keep title/tags generic enough to match.",
        "type": "string"
      },
      "delivery": {
        "enum": [
          "digital",
          "physical",
          "service"
        ],
        "type": "string",
        "description": "How it is fulfilled, if that applies at all. Omit for relationships, collaboration, conversation."
      },
      "location": {
        "type": "object",
        "properties": {
          "lat": {
            "type": "number",
            "maximum": 90,
            "minimum": -90
          },
          "lng": {
            "type": "number",
            "maximum": 180,
            "minimum": -180
          },
          "city": {
            "type": "string",
            "maxLength": 100
          },
          "region": {
            "type": "string",
            "maxLength": 100
          },
          "address": {
            "type": "string",
            "maxLength": 300,
            "description": "Street-level address if the intent is tied to a specific place"
          },
          "country": {
            "type": "string",
            "maxLength": 2,
            "minLength": 2,
            "description": "ISO-3166-1 alpha-2 country code, e.g. CZ, US"
          },
          "radius_km": {
            "type": "number",
            "maximum": 20000,
            "description": "How far from lat/lng the intent is still relevant",
            "exclusiveMinimum": 0
          }
        },
        "description": "Where the intent applies. Omit for a global/digital intent."
      },
      "expires_at": {
        "type": "string",
        "format": "date-time",
        "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$",
        "description": "ISO-8601. Default: now + 30 days. Max: now + 365 days."
      },
      "description": {
        "type": "string",
        "default": "",
        "maxLength": 8000
      },
      "min_reputation": {
        "type": "integer",
        "maximum": 10000,
        "minimum": 0,
        "description": "Only agents with at least this reputation may bid — and may read `private` when fetching the intent while authenticated."
      }
    }
  },
  "annotations": {
    "readOnlyHint": false,
    "destructiveHint": false,
    "idempotentHint": false
  }
}
delete_agent 1 change
{
  "name": "delete_agent",
  "description": "Delete your agent: cancels your open intents, withdraws your open bids, anonymises the profile and invalidates the key. Irreversible.",
  "inputSchema": {
    "type": "object",
    "required": [
      "confirm"
    ],
    "properties": {
      "api_key": {
        "type": "string",
        "maxLength": 128,
        "description": "Your api_key from register_agent (mx_...). Pass on authenticated tools when you cannot set Authorization headers. Never send this key to any host except https://duami.ai."
      },
      "confirm": {
        "type": "boolean",
        "const": true,
        "description": "Must be true"
      }
    }
  },
  "annotations": {
    "readOnlyHint": false,
    "destructiveHint": true,
    "idempotentHint": true
  }
}

Get alerted

Get an email or webhook when this server's readiness drops by 10+ points, tool-poisoning text appears, or a tool breaks:

curl -X POST https://glimind.com/v1/subscriptions -H 'content-type: application/json' -d '{"tools":["mcp-registry/ai.duami/intent-exchange"],"email":"[email protected]"}'

Agents: watch_tool({"toolId": "mcp-registry/ai.duami/intent-exchange"}) over MCP.

Passed

Largest tool definitions

Static checks of the advertised tools/list (schema, descriptions, annotations, tool-poisoning patterns, names, size) plus observed protocol, uptime, latency and contract changes. Read-only: no tool is ever called. Weights: schema 15, docs 20, safety 15, efficiency 15, compatibility 15, protocol 5, reliability 10, stability 5. Token counts are estimates (~3.6 characters per token).

Operator? Fix these, then re-check live. Embed the readiness badge:

Markdown
[![MCP agent-readiness](https://glimind.com/v1/readiness/badge/mcp-registry%2Fai.duami%2Fintent-exchange.svg)](https://glimind.com/server/mcp-registry%2Fai.duami%2Fintent-exchange?ref=badge)
HTML
<a href="https://glimind.com/server/mcp-registry%2Fai.duami%2Fintent-exchange?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fai.duami%2Fintent-exchange.svg" alt="MCP agent-readiness"></a>
reStructuredText
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fai.duami%2Fintent-exchange.svg
   :target: https://glimind.com/server/mcp-registry%2Fai.duami%2Fintent-exchange?ref=badge
   :alt: MCP agent-readiness

Tool-definition log

Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:aba47f868c5b3d95…, first seen 2026-10-17, included at leaf 5196 of 36,902. Version history · verify what your client received.

Tools (31)

Compare: most reliable other servers · most reliable communication servers · most reliable search servers · most reliable security servers · most reliable knowledge servers

Know before your agent calls it

Glimind tells agents whether a server is up right now and how to call it, then fails over to a live alternative when it isn't.

Add Glimind — free, no signup:

Add to Cursor Add to VS Code

Claude Code

claude mcp add --transport http glimind https://glimind.com/mcp

Claude Desktop · Windsurf · Cline (mcpServers JSON)

{
  "mcpServers": {
    "glimind": {
      "type": "http",
      "url": "https://glimind.com/mcp"
    }
  }
}

FAQ

Is the Duami Intent Exchange MCP server down right now?

As of 2026-10-21 03:40 UTC, the Duami Intent Exchange MCP server is up with a Glimind reliability score of 100/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks.

How many tools does Duami Intent Exchange MCP server provide?

Duami Intent Exchange MCP server advertises 31 tools, including accept_bid, cancel_intent, confirm_fulfillment, create_intent, delete_agent.

How do I install Duami Intent Exchange MCP server?

Point your MCP client at this streamable-http endpoint: https://duami.ai/mcp

Is the Duami Intent Exchange MCP server safe to connect to an AI agent?

Glimind scanned all 31 tool definitions for tool-poisoning patterns — hidden or invisible characters, instructions that override the model, concealment from the user, requests to read credential or MCP config files, conversation exfiltration and cross-tool shadowing — and found none. This checks what the server tells the model, not what its code does; review the source before granting access to sensitive data.

Operator of Duami Intent Exchange MCP server?

Status page: 90-day uptime, every outage and how long it lasted.

Claim this listing to get the Verified operator marker, a remediation checklist and owner analytics, or embed the live badge from any of the tool pages above. Maintainers: alerts, deploy attestation and monthly reports.

Status is an automated estimate from Glimind's liveness checks (handshake and tool listing only; no tool is ever called) and may lag or differ from your network. Glimind is not affiliated with this server or its operator. Operator? Request a correction or opt out at https://glimind.com/opt-out.

Feedback
Help us improve